Agent skill

Implementing Data Protection By Default

by mukul975 in mukul975/Privacy-Data-Protection-Skills

Technical implementation of GDPR Article 25(2) data protection by default.

Apache-2.0Auto-check passedLegal & Compliance

Install Implementing Data Protection By Default

skills CLI
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill implementing-data-protection-by-default -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Privacy-Data-Protection-Skills implementing-data-protection-by-default --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/privacy/implementing-data-protection-by-default .claude/skills/implementing-data-protection-by-default && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
implementing-data-protection-by-default
GitHub stars
295
Token cost
~2.5k tokens
SKILL.md length
1,186 words
Files
5 (incl. scripts, references, assets)
Skills in repo
278
Repo updated
First seen
Licence
Apache-2.0

At a glance

Technical implementation of GDPR Article 25(2) data protection by default.

  • Works in 4 steps: Amount of personal data collected → Extent of processing performed → Period of storage → …
  • Tasks that involve Privacy and GDPR
  • SKILL.md covers Overview, The Four Dimensions of…, Technical Implementation… and By-Default Verification Process, plus 1 more section
  • Runs Python scripts from its folder

What it does

Implementing Data Protection By Default is an agent skill from mukul975/Privacy-Data-Protection-Skills. Technical implementation of GDPR Article 25(2) data protection by default. Covers strictest privacy settings as default configuration, minimum data collection, limited storage duration, restricted accessibility, and opt-in rather than opt-out patterns. Includes implementation checklist and system design requirements.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/standards.md` and `references/workflows.md`).

It sits in Legal & Compliance, covering Privacy and GDPR. The repository describes itself as: 282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Privacy and GDPR

Example prompts

  • “/implementing-data-protection-by-default”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Amount of personal data collected
  2. Extent of processing performed
  3. Period of storage
  4. Accessibility of personal data

What it can do on your machine

Read from SKILL.md and the folder at commit 9b2ef9e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Implementing Data Protection By Default loads about 2.5k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 1,186 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mukul975/Privacy-Data-Protection-Skills at commit 9b2ef9e, republished under its Apache-2.0 licence (© mukul975). 1,186 words, ~2,502 tokens.

Download SKILL.mdSave it as .claude/skills/implementing-data-protection-by-default/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
implementing-data-protection-by-default
description
Technical implementation of GDPR Article 25(2) data protection by default. Covers strictest privacy settings as default configuration, minimum data collection, limited storage duration, restricted accessibility, and opt-in rather than opt-out patterns. Includes implementation checklist and system design requirements.
license
Apache-2.0
metadata.author
mukul975
metadata.version
1.0
metadata.domain
privacy
metadata.subdomain
privacy-by-design
metadata.tags
data-protection-by-default, article-25, privacy-defaults, opt-in, minimum-collection

Implementing Data Protection by Default

Overview

GDPR Article 25(2) requires that controllers implement appropriate technical and organisational measures for ensuring that, by default, only personal data which are necessary for each specific purpose of the processing are processed. This obligation applies across four dimensions:

  1. Amount of personal data collected
  2. Extent of processing performed
  3. Period of storage
  4. Accessibility of personal data

The EDPB Guidelines 4/2019 on Article 25 clarify that "by default" means the strictest privacy settings apply automatically, without requiring any action from the data subject. The data subject should not need to take action to protect their privacy — the system does it for them.

The Four Dimensions of By-Default Protection

Dimension 1: Minimum Data Collection (Amount)

Principle: By default, collect only the data fields strictly necessary for the core service purpose. Additional data collection requires explicit opt-in.

Default StateOpt-In StateExample
Core fields onlyExtended profileAccount creation collects email + display_name only; phone, address, photo collected only if user activates billing or delivery features
No location dataLocation-enabled featuresMobile app does not request location permission by default; only requests when user activates location-dependent feature
No behavioral trackingAnalytics opt-inWebsite loads without analytics cookies; tracking begins only after user grants consent in cookie banner
Minimal form fieldsProgressive disclosureRegistration form shows 3 required fields; optional fields appear only when user clicks "Add more information"

Prism Data Systems AG Implementation: The default customer registration at Prism Data Systems AG collects exactly three fields: email, display_name, and country_code. The country code is needed for regulatory compliance (determining applicable data protection law). All other fields (phone number, billing address, company name, job title) are collected only when the user activates a feature that requires them (billing module, enterprise integration, support escalation).

Dimension 2: Minimum Processing (Extent)

Principle: By default, process data only for the primary purpose. Secondary processing (analytics, profiling, marketing) requires explicit opt-in.

Processing ActivityDefault StateOpt-In Required
Core service deliveryActive (Art. 6(1)(b))No
Product analyticsDisabledYes — consent toggle in preference center
Marketing communicationsDisabledYes — separate consent at registration
Profiling for recommendationsDisabledYes — explicit opt-in with explanation
Third-party data sharingDisabledYes — named third party + purpose
Automated decision-makingDisabledYes — Art. 22 explicit consent

Prism Data Systems AG Implementation: New customer accounts at Prism Data Systems AG have all optional processing activities disabled by default. The account dashboard shows five processing toggles, all set to OFF:

  • Product analytics: OFF
  • Marketing emails: OFF
  • Feature recommendations: OFF
  • Usage data for ML training: OFF
  • Anonymous benchmarking contributions: OFF
Dimension 3: Minimum Storage (Period)

Principle: By default, apply the shortest defensible retention period. Longer retention requires justification tied to a specific legal obligation.

Data CategoryDefault RetentionExtended Retention (Justified)
Session dataDeleted at session endNot applicable
Server logs90 days12 months (security investigation)
Customer account dataAccount duration + 30 days+ statutory period (tax: 10 years for billing)
Support tickets1 year after closure3 years (limitation period)
Marketing consent recordsConsent duration + 3 years+ 5 years (accountability, Art. 7(1))
Analytics data13 monthsNot applicable (maximum)

Prism Data Systems AG Implementation: The retention policy engine at Prism Data Systems AG applies the shortest retention period by default for each data category. Extended retention is applied only for data categories with documented statutory requirements (tax records: 10 years per Swiss CO Art. 958f). All other data follows the purpose-based minimum retention.

Dimension 4: Minimum Accessibility

Principle: By default, restrict access to personal data to the minimum set of roles necessary. Broader access requires explicit authorization.

RoleDefault AccessElevated Access (Requires Justification)
Customer support (Tier 1)Masked PII only (m***@domain.ch)Unmasked PII (30-min timeout, ticket reference required)
Analytics teamPseudonymized data onlyNo access to direct identifiers
Engineering teamNo production PII accessBreak-glass access (dual approval, logged, time-limited)
Marketing teamAggregate statistics onlyNo individual-level data access
DPOFull access for compliance investigationsStanding access with audit trail
External auditorAnonymized samplesPurpose-limited access with NDA

Prism Data Systems AG Implementation: All new employee accounts at Prism Data Systems AG are provisioned with zero personal data access by default. Access is granted per-purpose through an access request workflow requiring manager approval and DPO notification. Access grants expire after 90 days and must be renewed. The Tier 1 support dashboard displays dynamically masked data by default.

Show full SKILL.md (461 more words)Show less

Technical Implementation Checklist

User Interface Defaults
  • All consent toggles default to OFF (unticked)
  • Privacy settings page accessible from main navigation
  • No pre-selected optional data collection
  • No dark patterns (no misleading button labels, no visual emphasis on "Accept All")
  • Cookie banner defaults to "Reject All" with equal visual prominence to "Accept All"
  • Registration form shows only mandatory fields by default
  • Notification preferences default to minimum (transactional only)
  • Profile visibility defaults to private (not public)
  • Data sharing toggles default to OFF for each third party
  • Search engine indexing of profiles defaults to OFF
Backend Defaults
  • API endpoints reject non-allowlisted fields (return 400 for unexpected fields)
  • New database tables include TTL metadata columns by default
  • Default retention period applied automatically unless longer period is explicitly configured
  • Pseudonymization applied at analytics ingestion boundary by default
  • Field-level encryption enabled for all PII columns by default
  • Dynamic masking rules applied to all support and operations dashboards
  • Audit logging enabled for all personal data access by default
  • Minimum group size (11) enforced on all analytics outputs
  • Cross-purpose data access blocked by default (requires compatibility assessment)
  • New service deployments fail privacy gate if data minimization assessment is not completed
Access Control Defaults
  • New employee accounts provisioned with zero personal data access
  • Access grants expire after 90 days by default
  • Elevated access requires documented justification and approval
  • Break-glass access logged and reviewed within 24 hours
  • Third-party access disabled by default until DPA is executed
  • API keys scoped to minimum required data categories
Communication Defaults
  • Marketing communications disabled for all new accounts
  • Transactional emails only (account confirmations, security alerts)
  • Push notifications limited to security alerts by default
  • Newsletter subscription requires separate opt-in
  • Partner communications disabled by default

By-Default Verification Process

  1. New account audit — Create a test account through the standard registration flow. Verify that no optional processing is active, no marketing communications are scheduled, and the minimum data fields are collected.

  2. Dashboard inspection — Log in as a Tier 1 support agent. Verify that all PII is masked by default and that unmasking requires explicit action with justification.

  3. API testing — Send API requests with additional fields beyond the allowlist. Verify that extra fields are rejected (HTTP 400).

  4. Retention verification — Check that newly created records have TTL metadata set according to the minimum retention period.

  5. Analytics output — Run a standard analytics query. Verify that results are pseudonymized, minimum group size is enforced, and differential privacy noise is applied.

Key Regulatory References

  • GDPR Article 25(2) — Data protection by default
  • GDPR Article 25(1) — Data protection by design
  • GDPR Recital 78 — Technical measures for data protection by default
  • EDPB Guidelines 4/2019 on Article 25, Section 3: Data Protection by Default
  • CJEU C-673/17 (Planet49) — Pre-ticked boxes do not constitute consent
  • EDPB Guidelines 05/2020 on consent — Consent must be freely given, not default

© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references, assets) in skills/privacy/implementing-data-protection-by-default of mukul975/Privacy-Data-Protection-Skills.

  • SKILL.md
  • assets/template.md
  • references/standards.md
  • references/workflows.md
  • scripts/process.py

Open the folder on GitHubat commit 9b2ef9e

Compare with similar skills

Implementing Data Protection By Default next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Implementing Data Protection By Default compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implementing Data Protection By Default this skillmukul975/Privacy-Data-Protection-Skills295—~2.5kAutomated safety check: PassApache-2.0
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Korean Privacy Termskimlawtech/korean-privacy-terms586—~2.9kAutomated safety check: PassApache-2.0
Gdpr ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9421 repos~3.9kAutomated safety check: PassMIT
Hipaa ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9421 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed
  • Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.

    5.5k GitHub stars~1.7k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Korean Privacy Terms

    kimlawtech/korean-privacy-terms

    처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). An agent skill from kimlawtech/korean-privacy-terms.

    586 GitHub stars~2.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Gdpr Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert GDPR compliance assistant covering all four core workflows: (1) auditing code and systems for GDPR violations, (2) drafting GDPR-compliant documents such as privacy policies, Data Processing…

    942 GitHub starsUsed in 1 repo~3.9k tokens
    Legal & ComplianceAuto-check passed
  • Hipaa Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert HIPAA compliance assistant for healthcare and software contexts.

    942 GitHub starsUsed in 1 repo~2.3k tokens
    Legal & ComplianceAuto-check passed
  • Pii Contract Analyze

    gregmos/PII-Shield

    Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.

    149 GitHub stars~8.9k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check: notes

More from mukul975/Privacy-Data-Protection-Skills

All 278 skills in this repo
  • Age Gating Services

    mukul975/Privacy-Data-Protection-Skills

    Implements age-gating mechanisms for online services to restrict access based on user age.

    295 GitHub stars~3.7k tokensUpdated 6 mo ago
    Auto-check passed
  • AI Data Retention

    mukul975/Privacy-Data-Protection-Skills

    Manages AI model retention and machine unlearning requirements.

    295 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Dpia Mitigation Plan

    mukul975/Privacy-Data-Protection-Skills

    Structures risk mitigation planning and residual risk tracking for Data Protection Impact Assessments under GDPR Article 35(7)(d).

    295 GitHub stars~846 tokensUpdated 6 mo ago
    Auto-check passed
  • Gdpr Accountability

    mukul975/Privacy-Data-Protection-Skills

    Guides implementation of the GDPR accountability principle under Articles 5(2) and 24, including documentation requirements for policies, DPIAs, RoPA, training records, and breach logs.

    295 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed
  • Pia Threshold Screening

    mukul975/Privacy-Data-Protection-Skills

    Conducts pre-DPIA threshold screening to determine whether a full Data Protection Impact Assessment is required under GDPR Article 35.

    295 GitHub stars~880 tokensUpdated 6 mo ago
    Auto-check passed
  • Retention Schedule

    mukul975/Privacy-Data-Protection-Skills

    Designs and implements data retention schedules compliant with GDPR Article 5(1)(e) storage limitation principle.

    295 GitHub stars~3.3k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Implementing Data Protection By Default

What does Implementing Data Protection By Default do?

Technical implementation of GDPR Article 25(2) data protection by default. Implementing Data Protection By Default is an agent skill from mukul975/Privacy-Data-Protection-Skills. Technical implementation of GDPR Article 25(2) data protection by default.

When should I use Implementing Data Protection By Default?

Implementing Data Protection By Default fits situations like: tasks that involve Privacy and GDPR.

How do I install Implementing Data Protection By Default in Claude Code?

Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill implementing-data-protection-by-default -a claude-code`. Or copy the skill folder (skills/privacy/implementing-data-protection-by-default in mukul975/Privacy-Data-Protection-Skills) into .claude/skills/implementing-data-protection-by-default in your project. Claude Code loads it when a task matches its description.

How do I install Implementing Data Protection By Default in Codex?

Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill implementing-data-protection-by-default -a codex`. Or copy the skill folder (skills/privacy/implementing-data-protection-by-default in mukul975/Privacy-Data-Protection-Skills) into .agents/skills/implementing-data-protection-by-default in your project. Codex loads it when a task matches its description.

Can I use Implementing Data Protection By Default in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill implementing-data-protection-by-default -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implementing-data-protection-by-default, .gemini/skills/implementing-data-protection-by-default, .github/skills/implementing-data-protection-by-default and .opencode/skills/implementing-data-protection-by-default in your project.

What does Implementing Data Protection By Default need to run?

Going by SKILL.md and its folder, Implementing Data Protection By Default needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Implementing Data Protection By Default access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Implementing Data Protection By Default safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Implementing Data Protection By Default use?

Implementing Data Protection By Default is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Implementing Data Protection By Default use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.

What are the alternatives to Implementing Data Protection By Default?

Skills that share tags, products or a category with Implementing Data Protection By Default: C15t (c15t/c15t, 1.9k stars), HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), Korean Privacy Terms (kimlawtech/korean-privacy-terms, 586 stars) and Gdpr Compliance (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 942 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implementing Data Protection By Default?

mukul975 (a GitHub user) maintains it in mukul975/Privacy-Data-Protection-Skills, which has 295 GitHub stars. The repository holds 278 skills in this directory. The repository was last updated on March 16, 2026.

Source: mukul975/Privacy-Data-Protection-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.